Cooperative Detour Planning for Dual-Task Drone Fleets

TL;DR

This paper presents a decentralized drone fleet framework for simultaneous urban delivery and traffic monitoring, optimizing routes to maximize traffic data collection while respecting delivery and battery constraints.

Contribution

It introduces a local clustering and meet-and-merge strategy enabling scalable, near-optimal traffic monitoring in urban drone fleets without centralized computation.

Findings

Decentralized approach outperforms shortest-path policy in traffic data collection.

Meet-and-merge strategy achieves near-global optimal coverage.

Simulation on Barcelona's city network demonstrates efficiency and effectiveness.

Abstract

As Urban air mobility scales, commercial drone fleets offer a compelling, yet underexplored opportunity to function as mobile sensor networks for real-time urban traffic monitoring. In this paper, we propose a decentralized framework that enables drone fleets to simultaneously execute delivery tasks and observe network traffic conditions. We model the urban environment with dynamic information values associated with road segments, which accumulate traffic condition uncertainty over time and are reset upon drone visitation. This problem is formulated as a mixed-integer linear programming problem where drones maximize the traffic information reward while respecting the maximum detour for each delivery and the battery budget of each drone. Unlike centralized approaches that are computationally heavy for large fleets, our method focuses on dynamic local clustering. When drones enter communication range, they exchange their belief in traffic status and transition from isolated path planning to a local joint optimization mode, resolving coupled constraints to obtain replanned paths for each drone, respectively. Simulation results built on the real city network of Barcelona, Spain, demonstrate that, compared to a shortest-path policy that ignores the traffic monitoring task, our proposed method better utilizes the battery and detour budget to explore the city area and obtain adequate traffic information; and, thanks to its decentralized manner, this ``meet-and-merge" strategy achieves near-global optimality in network coverage with significantly reduced computation overhead compared to the centralized baseline.